Articles | Volume 18, issue 19
https://doi.org/10.5194/gmd-18-6903-2025
https://doi.org/10.5194/gmd-18-6903-2025
Development and technical paper
 | 
08 Oct 2025
Development and technical paper |  | 08 Oct 2025

Enhanced land subsidence interpolation through a hybrid deep convolutional neural network and InSAR time series

Zahra Azarm, Hamid Mehrabi, and Saeed Nadi

Cited articles

Abdollahi, S., Pourghasemi, H. R., Ghanbarian, G. A., and Safaeian, R.: Prioritization of effective factors in the occurrence of land subsidence and its susceptibility mapping using an SVM model and their different kernel functions, B. Eng. Geol. Environ., 78, 4017–4034, https://doi.org/10.1007/s10064-018-1403-6, 2019. 
Amighpey, M. and Arabi, S.: Studying land subsidence in Yazd province, Iran, by integration of InSAR and levelling measurements, Remote Sens. Appl.: Soc. Environ., 4, 1–8, https://doi.org/10.1016/j.rsase.2016.04.001, 2016. 
Andaryani, S., Nourani, V., Trolle, D., Dehghani, M., and Asl, A. M.: Assessment of land use and climate change effects on land subsidence using a hydrological model and radar technique, J. Hydrol., 578, 124070, https://doi.org/10.1016/j.jhydrol.2019.124070, 2019. 
Azarakhsh, Z., Azadbakht, M., and Matkan, A.: Estimation, modeling, and prediction of land subsidence using Sentinel-1 time series in Tehran-Shahriar plain: A machine learning-based investigation, Remote Sens. Appl.: Soc. Environ., 25, 100691, https://doi.org/10.1016/j.rsase.2021.100691, 2022. 
Azarm, Z.: Enhanced Land Subsidence Interpolation through a Hybrid Deep Convolutional Neural Network and InSAR Time Series, Zenodo [code], https://doi.org/10.5281/zenodo.12721120, 2024. 
Download
Short summary
The article introduces a new method to estimate land subsidence using deep convolutional neural networks (CNNs) and persistent scatterer interferometric synthetic aperture radar (PSInSAR), addressing the limitations of traditional methods. It focuses on Isfahan Province, Iran, and demonstrates substantial improvement over conventional techniques. The deep CNN method showed a 70 % enhancement in subsidence prediction, with the study area experiencing over 38 cm of subsidence between 2014 and 2020.
Share